Abstract

We present two different approaches to apply deep learning to inverse design for nanophotonic devices. First, we use a regression model, with device parameters as inputs and device responses as outputs, or vice versa. Second, we use a novel generative model to create a series of improved designs. We demonstrate them to design nanophotonic power splitters with multiple splitting ratios.

© 2020 The Author(s)

PDF Article
More Like This
Inverse Design of Nanophotonic Devices using Deep Neural Networks

Keisuke Kojima, Yingheng Tang, Toshiaki Koike-Akino, Ye Wang, Devesh Jha, Kieran Parsons, Mohammad H. Tahersima, Fengqiao Sang, Jonathan Klamkin, and Minghao Qi
Su1A.1 Asia Communications and Photonics Conference (ACPC) 2020

Deep Neural Network Inverse Modeling for Integrated Photonics

Mohammad H. Tahersima, Keisuke Kojima, Toshiaki Koike-Akino, Devesh Jha, Bingnan Wang, Chungwei Lin, and Kieran Parsons
W3B.5 Optical Fiber Communication Conference (OFC) 2019

Deep Convolutional Neural Network for the Inverse Design of Layered Photonic Structures

Rohit Unni, Kan Yao, and Yuebing Zheng
JW2D.14 CLEO: Applications and Technology (CLEO_AT) 2020

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription